Multitask Online Learning: Listen to the Neighborhood Buzz

arXiv:2310.17385v2 Announce Type: replace
Abstract: We study multitask online learning in a setting where agents can only exchange information with their neighbors on an arbitrary communication network. We introduce $\texttt{MT-CO}_2\texttt{OL}$, a decentralized algorithm for this setting whose regret depends on the interplay between the task similarities and the network structure. Our analysis shows that the regret of $\texttt{MT-CO}_2\texttt{OL}$ is never worse (up to constants) than the bound obtained when agents do not share information. On the other hand, our bounds …

abstract agents algorithm analysis arxiv communication cs.lg decentralized information neighbors network online learning study type